📘👐 Vector Quantization

Vector Quantization is a technique to reduce the number of bits that represent a vector. This can help reduce the storage and memory requirements for vector embeddings.

Atlas Vector Search supports automatic quantization of double or 32-bit float values in your vector embeddings. You can set the quantization method for vector type fields in your index definition.

📚 Vector Quantization

CODE_BLOCK_16

Answer

{
    "name": ATLAS_VECTOR_SEARCH_INDEX_NAME,
    "type": "vectorSearch",
    "definition": {
        "fields": [
            {
                "type": "vector",
                "path": "embedding",
                "numDimensions": 512,
                "similarity": "cosine",
                "quantization": "scalar",
            },
        ]
    },
}